{"id":"https://openalex.org/W4286377487","doi":"https://doi.org/10.1109/tnnls.2022.3190246","title":"Stochastic Optimal Control for Multivariable Dynamical Systems Using Expectation Maximization","display_name":"Stochastic Optimal Control for Multivariable Dynamical Systems Using Expectation Maximization","publication_year":2022,"publication_date":"2022-07-21","ids":{"openalex":"https://openalex.org/W4286377487","doi":"https://doi.org/10.1109/tnnls.2022.3190246","mag":"3090720308","pmid":"https://pubmed.ncbi.nlm.nih.gov/35862333"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2022.3190246","doi":"https://doi.org/10.1109/tnnls.2022.3190246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3190246","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.00207","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068664769","display_name":"Prakash Mallick","orcid":"https://orcid.org/0000-0002-3535-5464","observed_orcids":["https://orcid.org/0000-0002-3535-5464"]},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Prakash Mallick","raw_affiliation_strings":["School of Engineering, The University of Newcastle, Callaghan, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-3535-5464","affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Newcastle, Callaghan, NSW, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100370053","display_name":"Zhiyong Chen","orcid":"https://orcid.org/0000-0002-2033-4249","observed_orcids":["https://orcid.org/0000-0002-2033-4249","https://orcid.org/0009-0002-5160-3779","https://orcid.org/0009-0004-9423-1869","https://orcid.org/0009-0005-2555-5728"]},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zhiyong Chen","raw_affiliation_strings":["School of Engineering, The University of Newcastle, Callaghan, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-2033-4249","affiliations":[{"raw_affiliation_string":"School of Engineering, The University of Newcastle, Callaghan, NSW, Australia","institution_ids":["https://openalex.org/I78757542"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I78757542"],"apc_list":{"value":2195,"currency":"USD","value_usd":2195},"apc_paid":null,"fwci":0.3983,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.54972163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"34","issue":"9","first_page":"5268","last_page":"5282"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6714000105857849,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6714000105857849,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.20679999887943268,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.1103999987244606,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stochastic-optimal-control","display_name":"stochastic optimal control","score":1.0},{"id":"https://openalex.org/keywords/trajectory-optimization","display_name":"trajectory optimization","score":0.9940000176429749},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.9829999804496765},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5899999737739563},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9369999766349792},{"id":"https://openalex.org/keywords/measurement-noise","display_name":"measurement noise","score":0.9319999814033508},{"id":"https://openalex.org/keywords/control-parameter-estimation","display_name":"control parameter estimation","score":0.6330000162124634},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.7590000033378601}],"concepts":[{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6529767513275146},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5690419673919678},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.5604274272918701},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.5529016256332397},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.5334218740463257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5290730595588684},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5132274627685547},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.493040531873703},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.45851847529411316},{"id":"https://openalex.org/C194387892","wikidata":"https://www.wikidata.org/wiki/Q1747770","display_name":"Stochastic optimization","level":2,"score":0.4569869041442871},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.43054527044296265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37919697165489197},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3301458954811096},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/tnnls.2022.3190246","doi":"https://doi.org/10.1109/tnnls.2022.3190246","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2022.3190246","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-b","cwts-core","dongbi-a","doyens","jufo-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:35862333","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35862333","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2010.00207","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00207","pdf_url":"https://arxiv.org/pdf/2010.00207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3090720308","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2010.00207.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:uon:43629","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/1959.13/1449269","pdf_url":null,"source":{"id":"https://openalex.org/S4377196471","display_name":"NOVA (University of Newcastle Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I78757542","host_organization_name":"University of Newcastle Australia","host_organization_lineage":["https://openalex.org/I78757542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"},{"id":"doi:10.48550/arxiv.2010.00207","doi":"https://doi.org/10.48550/arxiv.2010.00207","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2010.00207","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.00207","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.00207","pdf_url":"https://arxiv.org/pdf/2010.00207","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4286377487.pdf","grobid_xml":"https://content.openalex.org/works/W4286377487.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W572470661","https://openalex.org/W1486034269","https://openalex.org/W1529094214","https://openalex.org/W1529817735","https://openalex.org/W1586251222","https://openalex.org/W1679945064","https://openalex.org/W1687873425","https://openalex.org/W1923344279","https://openalex.org/W1963763873","https://openalex.org/W2003967703","https://openalex.org/W2011691068","https://openalex.org/W2012392077","https://openalex.org/W2012587148","https://openalex.org/W2029321550","https://openalex.org/W2032100464","https://openalex.org/W2053742104","https://openalex.org/W2080039641","https://openalex.org/W2087617385","https://openalex.org/W2098432798","https://openalex.org/W2107464055","https://openalex.org/W2107662876","https://openalex.org/W2111467524","https://openalex.org/W2117853077","https://openalex.org/W2119567691","https://openalex.org/W2120070743","https://openalex.org/W2121103318","https://openalex.org/W2123157758","https://openalex.org/W2134136353","https://openalex.org/W2140135625","https://openalex.org/W2144088174","https://openalex.org/W2149860990","https://openalex.org/W2150695437","https://openalex.org/W2161064850","https://openalex.org/W2167117957","https://openalex.org/W2211399972","https://openalex.org/W2414024437","https://openalex.org/W2508728158","https://openalex.org/W2510228645","https://openalex.org/W2604726708","https://openalex.org/W2963630259","https://openalex.org/W2963962369","https://openalex.org/W2964161785","https://openalex.org/W3090974819","https://openalex.org/W4210616753","https://openalex.org/W4212863985","https://openalex.org/W4230690906","https://openalex.org/W4232832013","https://openalex.org/W4237733001","https://openalex.org/W4239125046","https://openalex.org/W4281258657","https://openalex.org/W6657595581","https://openalex.org/W6681478256","https://openalex.org/W6903351479","https://openalex.org/W6903373895"],"related_works":["https://openalex.org/W3090720308","https://openalex.org/W4390214683","https://openalex.org/W7070426337","https://openalex.org/W4408522761","https://openalex.org/W3135618912","https://openalex.org/W3090974819","https://openalex.org/W2735992950","https://openalex.org/W7127976642","https://openalex.org/W2885898206","https://openalex.org/W4403599245"],"abstract_inverted_index":{"Trajectory":[0],"optimization":[1,16,107,119],"is":[2,114,132,146,160],"a":[3,14,74,80],"fundamental":[4],"stochastic":[5,32,77],"optimal":[6,93],"control":[7,40,78,94,151,157],"(SOC)":[8],"problem.":[9],"This":[10,84,117],"article":[11],"deals":[12],"with":[13,65,96],"trajectory":[15,106,118],"approach":[17],"for":[18],"dynamical":[19],"systems":[20],"subject":[21],"to":[22,36,148],"measurement":[23],"noise":[24],"that":[25],"can":[26],"be":[27],"fitted":[28],"into":[29],"linear":[30],"time-varying":[31],"models.":[33],"Exact/complete":[34],"solutions":[35,64],"these":[37],"kind":[38],"of":[39,55,76,86,91,99,126,150,155],"problems":[41],"have":[42],"been":[43],"deemed":[44],"analytically":[45],"intractable":[46],"in":[47,79,124,128],"literature":[48],"because":[49],"they":[50],"come":[51],"under":[52],"the":[53,89,97,156],"category":[54],"partially":[56],"observable":[57],"Markov":[58],"decision":[59],"processes":[60],"(MDPs).":[61],"Therefore,":[62],"effective":[63],"reasonable":[66],"approximations":[67],"are":[68],"widely":[69],"sought":[70],"for.":[71],"We":[72],"propose":[73],"reformulation":[75],"reinforcement":[81],"learning":[82],"setting.":[83],"type":[85],"formulation":[87],"assimilates":[88],"benefits":[90],"conventional":[92],"procedure,":[95],"advantages":[98],"maximum":[100],"likelihood":[101],"approaches.":[102],"Finally,":[103],"an":[104],"iterative":[105],"paradigm":[108],"called":[109],"as":[110],"SOC-expectation":[111],"maximization":[112],"(SOC-EM)":[113],"put":[115],"forth.":[116],"procedure":[120],"exhibits":[121],"better":[122],"performance":[123],"terms":[125],"reduction":[127],"cumulative":[129],"cost-to-go":[130],"which":[131,145,162],"proven":[133],"both":[134],"theoretically":[135],"and":[136,169],"empirically.":[137],"Furthermore,":[138],"we":[139],"also":[140],"provide":[141],"novel":[142],"theoretical":[143],"work":[144],"related":[147],"uniqueness":[149],"parameter":[152],"estimates.":[153],"Analysis":[154],"covariance":[158],"matrix":[159],"presented,":[161],"handles":[163],"stochasticity":[164],"through":[165],"efficiently":[166],"balancing":[167],"exploration":[168],"exploitation.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-07-21T00:00:00"}